Evaluating AI-Driven Automated Map Digitization in QGIS

2025-04-26

AI Summary

To address the high labor cost and low efficiency of conventional manual map vectorization, this study proposes and evaluates Deepness—a deep learning–based remote sensing plugin natively embedded in the QGIS ecosystem—enabling the first end-to-end, reproducible automated recognition and vectorization of map features. Methodologically, Deepness integrates deep neural networks with multi-source remote sensing image analysis, directly processing Google Earth imagery and conducting quantitative validation against manually curated OpenStreetMap vector ground truth. Experimental results demonstrate that Deepness achieves a mean Intersection-over-Union (IoU) of 86.3% on road and building extraction tasks, outperforming traditional semi-automatic approaches by a factor of five in processing speed and substantially reducing manual post-editing effort. Its core contribution lies in establishing the first deep learning–native, fully automated vectorization framework integrated into QGIS, thereby advancing the operational deployment of intelligent remote sensing interpretation within open-source GIS platforms.

Technology Category

• Computer Vision: Remote Sensing / Geospatial AI
• Machine Learning: Deep Learning Algorithms
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets

Abstract

Map digitization is an important process that converts maps into digital formats that can be used for further analysis. This process typically requires a deep human involvement because of the need for interpretation and decision-making when translating complex features. With the advancement of artificial intelligence, there is an alternative to conducting map digitization with the help of machine learning techniques. Deepness, or Deep Neural Remote Sensing, is an advanced AI-driven tool designed and integrated as a plugin in QGIS application. This research focuses on assessing the effectiveness of Deepness in automated digitization. This study analyses AI-generated digitization results from Google Earth imagery and compares them with digitized outputs from OpenStreetMap (OSM) to evaluate performance.

Problem

• Assessing AI-driven automated map digitization in QGIS
• Comparing AI-generated results with OpenStreetMap outputs
• Evaluating Deepness plugin effectiveness for digital conversion

Innovation

• AI-driven automated map digitization in QGIS
• Deep Neural Remote Sensing plugin integration
• Performance comparison with OpenStreetMap outputs